© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28024
    Prev
    Next
    INDEX
    Explanations

    i'm followed by verb or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bergen
    -0.09
    zelfde
    -0.08
    ork
    -0.08
    atum
    -0.08
    ymb
    -0.08
    glieder
    -0.08
    £¼
    -0.08
     pandang
    -0.07
    æĸĩ广
    -0.07
     shove
    -0.07
    POSITIVE LOGITS
    osit
    0.07
    åħ¶ä¸º
    0.06
    alisierung
    0.06
     sure
    0.06
    shire
    0.06
     Channel
    0.06
    dea
    0.06
     ÙħÙĤت
    0.06
    ordan
    0.06
    ship
    0.06
    Activations Density 0.226%

    No Known Activations